From 0f6217f507e3c208921f95d4812c3f49567a9419 Mon Sep 17 00:00:00 2001 From: Eugene Yurtsev Date: Tue, 13 Aug 2024 20:24:02 -0400 Subject: [PATCH] docs: together ai embeddings integration docs (#25252) Update together AI embedding integration docs Related issue: https://github.com/langchain-ai/langchain/issues/24856 ```json [ { "provider": "together", "js": true, "local": false, "serializable": false, } ] ``` --------- Co-authored-by: Isaac Francisco <78627776+isahers1@users.noreply.github.com> Co-authored-by: isaac hershenson --- .../text_embedding/together.ipynb | 233 ++++++++++++++---- 1 file changed, 188 insertions(+), 45 deletions(-) diff --git a/docs/docs/integrations/text_embedding/together.ipynb b/docs/docs/integrations/text_embedding/together.ipynb index 6f3cc393d1..16dd5aa3a1 100644 --- a/docs/docs/integrations/text_embedding/together.ipynb +++ b/docs/docs/integrations/text_embedding/together.ipynb @@ -12,101 +12,244 @@ }, { "cell_type": "markdown", - "id": "e49f1e0d", + "id": "9a3d6f34", "metadata": {}, "source": [ "# TogetherEmbeddings\n", "\n", - "This notebook covers how to get started with open source embedding models hosted in the Together AI API.\n", + "This will help you get started with Together embedding models using LangChain. For detailed documentation on `TogetherEmbeddings` features and configuration options, please refer to the [API reference](https://api.python.langchain.com/en/latest/embeddings/langchain_together.embeddings.TogetherEmbeddings.html).\n", "\n", - "## Installation" + "## Overview\n", + "### Integration details\n", + "\n", + "import { ItemTable } from \"@theme/FeatureTables\";\n", + "\n", + "\n", + "\n", + "## Setup\n", + "\n", + "To access Together embedding models you'll need to create a/an Together account, get an API key, and install the `langchain-together` integration package.\n", + "\n", + "### Credentials\n", + "\n", + "Head to [https://api.together.xyz/](https://api.together.xyz/) to sign up to Together and generate an API key. Once you've done this set the TOGETHER_API_KEY environment variable:" ] }, { "cell_type": "code", - "execution_count": null, - "id": "4c3bef91", + "execution_count": 1, + "id": "36521c2a", "metadata": {}, "outputs": [], "source": [ - "# install package\n", - "%pip install --upgrade --quiet langchain-together" + "import getpass\n", + "import os\n", + "\n", + "if not os.getenv(\"TOGETHER_API_KEY\"):\n", + " os.environ[\"TOGETHER_API_KEY\"] = getpass.getpass(\"Enter your Together API key: \")" ] }, { "cell_type": "markdown", - "id": "2b4f3e15", + "id": "c84fb993", "metadata": {}, "source": [ - "## Environment Setup\n", - "\n", - "Make sure to set the following environment variables:\n", - "\n", - "- `TOGETHER_API_KEY`\n", - "\n", - "## Usage\n", - "\n", - "First, select a supported model from [this list](https://docs.together.ai/docs/embedding-models). In the following example, we will use `togethercomputer/m2-bert-80M-8k-retrieval`." + "If you want to get automated tracing of your model calls you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:" ] }, { "cell_type": "code", - "execution_count": null, - "id": "62e0dbc3", - "metadata": { - "tags": [] - }, + "execution_count": 2, + "id": "39a4953b", + "metadata": {}, "outputs": [], "source": [ - "from langchain_together.embeddings import TogetherEmbeddings\n", + "# os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n", + "# os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")" + ] + }, + { + "cell_type": "markdown", + "id": "d9664366", + "metadata": {}, + "source": [ + "### Installation\n", "\n", - "embeddings = TogetherEmbeddings(model=\"togethercomputer/m2-bert-80M-8k-retrieval\")" + "The LangChain Together integration lives in the `langchain-together` package:" ] }, { "cell_type": "code", - "execution_count": null, - "id": "12fcfb4b", + "execution_count": 3, + "id": "64853226", "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n", + "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m24.0\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m24.2\u001b[0m\n", + "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpython -m pip install --upgrade pip\u001b[0m\n", + "Note: you may need to restart the kernel to use updated packages.\n" + ] + } + ], "source": [ - "embeddings.embed_query(\"My query to look up\")" + "%pip install -qU langchain-together" + ] + }, + { + "cell_type": "markdown", + "id": "45dd1724", + "metadata": {}, + "source": [ + "## Instantiation\n", + "\n", + "Now we can instantiate our model object and generate chat completions:" ] }, { "cell_type": "code", - "execution_count": null, - "id": "1f2e6104", + "execution_count": 5, + "id": "9ea7a09b", "metadata": {}, "outputs": [], "source": [ - "embeddings.embed_documents(\n", - " [\"This is a content of the document\", \"This is another document\"]\n", + "from langchain_together import TogetherEmbeddings\n", + "\n", + "embeddings = TogetherEmbeddings(\n", + " model=\"togethercomputer/m2-bert-80M-8k-retrieval\",\n", ")" ] }, + { + "cell_type": "markdown", + "id": "77d271b6", + "metadata": {}, + "source": [ + "## Indexing and Retrieval\n", + "\n", + "Embedding models are often used in retrieval-augmented generation (RAG) flows, both as part of indexing data as well as later retrieving it. For more detailed instructions, please see our RAG tutorials under the [working with external knowledge tutorials](/docs/tutorials/#working-with-external-knowledge).\n", + "\n", + "Below, see how to index and retrieve data using the `embeddings` object we initialized above. In this example, we will index and retrieve a sample document in the `InMemoryVectorStore`." + ] + }, { "cell_type": "code", - "execution_count": null, - "id": "46739f68", + "execution_count": 6, + "id": "d817716b", "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "'LangChain is the framework for building context-aware reasoning applications'" + ] + }, + "execution_count": 6, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# async embed query\n", - "await embeddings.aembed_query(\"My query to look up\")" + "# Create a vector store with a sample text\n", + "from langchain_core.vectorstores import InMemoryVectorStore\n", + "\n", + "text = \"LangChain is the framework for building context-aware reasoning applications\"\n", + "\n", + "vectorstore = InMemoryVectorStore.from_texts(\n", + " [text],\n", + " embedding=embeddings,\n", + ")\n", + "\n", + "# Use the vectorstore as a retriever\n", + "retriever = vectorstore.as_retriever()\n", + "\n", + "# Retrieve the most similar text\n", + "retrieved_documents = retriever.invoke(\"What is LangChain?\")\n", + "\n", + "# show the retrieved document's content\n", + "retrieved_documents[0].page_content" + ] + }, + { + "cell_type": "markdown", + "id": "e02b9855", + "metadata": {}, + "source": [ + "## Direct Usage\n", + "\n", + "Under the hood, the vectorstore and retriever implementations are calling `embeddings.embed_documents(...)` and `embeddings.embed_query(...)` to create embeddings for the text(s) used in `from_texts` and retrieval `invoke` operations, respectively.\n", + "\n", + "You can directly call these methods to get embeddings for your own use cases.\n", + "\n", + "### Embed single texts\n", + "\n", + "You can embed single texts or documents with `embed_query`:" ] }, { "cell_type": "code", - "execution_count": null, - "id": "e48632ea", + "execution_count": 7, + "id": "0d2befcd", "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[0.3812227, -0.052848946, -0.10564975, 0.03480297, 0.2878488, 0.0084609175, 0.11605915, 0.05303011, \n" + ] + } + ], "source": [ - "# async embed documents\n", - "await embeddings.aembed_documents(\n", - " [\"This is a content of the document\", \"This is another document\"]\n", - ")" + "single_vector = embeddings.embed_query(text)\n", + "print(str(single_vector)[:100]) # Show the first 100 characters of the vector" + ] + }, + { + "cell_type": "markdown", + "id": "1b5a7d03", + "metadata": {}, + "source": [ + "### Embed multiple texts\n", + "\n", + "You can embed multiple texts with `embed_documents`:" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "id": "2f4d6e97", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[0.3812227, -0.052848946, -0.10564975, 0.03480297, 0.2878488, 0.0084609175, 0.11605915, 0.05303011, \n", + "[0.066308185, -0.032866564, 0.115751594, 0.19082588, 0.14017, -0.26976448, -0.056340694, -0.26923394\n" + ] + } + ], + "source": [ + "text2 = (\n", + " \"LangGraph is a library for building stateful, multi-actor applications with LLMs\"\n", + ")\n", + "two_vectors = embeddings.embed_documents([text, text2])\n", + "for vector in two_vectors:\n", + " print(str(vector)[:100]) # Show the first 100 characters of the vector" + ] + }, + { + "cell_type": "markdown", + "id": "98785c12", + "metadata": {}, + "source": [ + "## API Reference\n", + "\n", + "For detailed documentation on `TogetherEmbeddings` features and configuration options, please refer to the [API reference](https://api.python.langchain.com/en/latest/embeddings/langchain_together.embeddings.TogetherEmbeddings.html).\n" ] } ], @@ -126,7 +269,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.10.5" + "version": "3.11.4" } }, "nbformat": 4,